Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Sunandita Patra"'
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:15377-15384
We describe ACR-SDN, a system to monitor, diagnose, and quickly respond to attacks or failures that may occur in software-defined networks (SDNs). An integral part of ACR-SDN is its use of RAE+UPOM, an automated acting and planning engine that uses h
Publikováno v:
Proceedings of the International Conference on Automated Planning and Scheduling. 31:225-233
We describe Dec-RPAE, a system for decentralized multi-agent acting and planning in partially observable and non-deterministic environments. The system includes both an acting component and an online planning component. The acting component is simila
Publikováno v:
The International FLAIRS Conference Proceedings. 35
When an actor executes a plan, action failures and exogenous events may lead to unexpected states that require replanning from the middle of plan execution. In Hierarchical Task Network (HTN) planning, unless the HTN methods have been carefully writt
Autor:
Sunandita Patra, Mark Cavolowsky, Onur Kulaksizoglu, Ruoxi Li, Laura Hiatt, Mark Roberts, Dana Nau
Publikováno v:
The International FLAIRS Conference Proceedings. 35
Hierarchy and curricula are two techniques commonly used to improve training for Reinforcement Learning (RL) agents. Yet few works have examined how to leverage hierarchical planning to generate a curriculum for training RL Options. We formalize a go
Publikováno v:
34th Florida Artificial Intelligence Research Society Conference (FLAIRS-34)
34th Florida Artificial Intelligence Research Society Conference (FLAIRS-34), May 2021, Miami, United States
FLAIRS Conference
34th Florida Artificial Intelligence Research Society Conference (FLAIRS-34), May 2021, Miami, United States
FLAIRS Conference
International audience; The coordination and control of hierarchically organized interacting agents is an important issue in many applications, e.g., harbor or warehouse automation. A formalism of agents as hierarchical input/output automata is propo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::930c55d449334f4571c817a10d699ed8
https://hal.laas.fr/hal-03211012/document
https://hal.laas.fr/hal-03211012/document
Publikováno v:
Artificial Intelligence
Artificial Intelligence, 2021, 299, pp.103523. ⟨10.1016/j.artint.2021.103523⟩
Artificial Intelligence, Elsevier, 2021, 299, pp.103523. ⟨10.1016/j.artint.2021.103523⟩
Artificial Intelligence, 2021, 299, pp.103523. ⟨10.1016/j.artint.2021.103523⟩
Artificial Intelligence, Elsevier, 2021, 299, pp.103523. ⟨10.1016/j.artint.2021.103523⟩
In AI research, synthesizing a plan of action has typically used descriptive models of the actions that abstractly specify what might happen as a result of an action, and are tailored for efficiently computing state transitions. However, executing th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::040c77992f5d08eef760933d1dcf54d3
http://arxiv.org/abs/2010.01909
http://arxiv.org/abs/2010.01909
Publikováno v:
Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19)
Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), Jan 2019, Honolulu, United States
AAAI
Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), Jan 2019, Honolulu, United States
AAAI
International audience; The most common representation formalisms for planning are descriptive models. They abstractly describe what the actions do and are tailored for efficiently computing the next state(s) in a state transition system. But acting
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ca3afc312518a2aec5df6dd77ce57fcf
https://hal.laas.fr/hal-01959110/document
https://hal.laas.fr/hal-01959110/document
Publikováno v:
Research and Development in Intelligent Systems XXX ISBN: 9783319026206
SGAI Conf.
SGAI Conf.
Heuristic search is a fundamental problem solving paradigm in artificial intelligence. We address the problem of developing heuristic search algorithms where intermediate results are sought at intervals of time which may or may not be known apriori.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::704f4736b7671ea79604cb1816657148
https://doi.org/10.1007/978-3-319-02621-3_10
https://doi.org/10.1007/978-3-319-02621-3_10